Changeset 14373

Timestamp:

11/05/16 09:06:31 (7 years ago)

Author:

gkronber

Message:

#745:

• using a line chart (IndexedDataTable) instead of a scatter plot
• added number of variables (non-zero coefficients) to the line chart

File:

• branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4/ElasticNetLinearRegression.cs (modified) (3 diffs)

branches/HeuristicLab.Algorithms.DataAnalysis.Glmnet/3.4/ElasticNetLinearRegression.cs

@@ -140 +140 @@
       var dataRows = new DataRow[nCoeff];
       var allowedVars = Problem.ProblemData.AllowedInputVariables.ToArray();
+      var numNonZeroCoeffs = new int[nLambdas];
       for (int i = 0; i < nCoeff; i++) {
         var coeffId = allowedVars[i];
@@ -147 +148 @@
         coeffTable.Rows.Add(dataRows[i]);
       }
+      for (int i = 0; i < coeff.GetLength(0); i++) {
+        for (int j = 0; j < coeff.GetLength(1); j++) {
+          if (!coeff[i, j].IsAlmost(0.0)) {
+            numNonZeroCoeffs[i]++;
+          }
+        }
+      }
 
       Results.Add(new Result(coeffTable.Name, coeffTable.Description, coeffTable));
 
-      var nmsePlot = new ScatterPlot("NMSE", "Path of NMSE values over different lambda values");
+      var nmsePlot = new IndexedDataTable<double>("NMSE", "Path of NMSE values over different lambda values");
       nmsePlot.VisualProperties.YAxisMaximumAuto = false;
       nmsePlot.VisualProperties.YAxisMinimumAuto = false;
@@ -158 +166 @@
       nmsePlot.VisualProperties.YAxisMinimumFixedValue = 0;
       nmsePlot.VisualProperties.YAxisMaximumFixedValue = 1.0;
+      nmsePlot.VisualProperties.XAxisLogScale = true;
       nmsePlot.VisualProperties.XAxisTitle = "Log10(Lambda)";
       nmsePlot.VisualProperties.YAxisTitle = "Normalized mean of squared errors (NMSE)";
-      nmsePlot.Rows.Add(new ScatterPlotDataRow("NMSE (train)", "Path of NMSE values over different lambda values", lambda.Zip(trainNMSE, (l, v) => new Point2D<double>(Math.Log10(l), v))));
-      nmsePlot.Rows.Add(new ScatterPlotDataRow("NMSE (test)", "Path of NMSE values over different lambda values", lambda.Zip(testNMSE, (l, v) => new Point2D<double>(Math.Log10(l), v))));
+      nmsePlot.VisualProperties.SecondYAxisTitle= "Number of variables";
+      nmsePlot.Rows.Add(new IndexedDataRow<double>("NMSE (train)", "Path of NMSE values over different lambda values", lambda.Zip(trainNMSE, (l, v) => Tuple.Create(l, v))));
+      nmsePlot.Rows.Add(new IndexedDataRow<double>("NMSE (test)", "Path of NMSE values over different lambda values", lambda.Zip(testNMSE, (l, v) => Tuple.Create(l, v))));
+      nmsePlot.Rows.Add(new IndexedDataRow<double>("Number of variables", "The number of non-zero coefficients for each step in the path", lambda.Zip(numNonZeroCoeffs, (l, v) => Tuple.Create(l, (double)v))));
       if (lambda.Length > 2) {
-        nmsePlot.VisualProperties.XAxisMinimumFixedValue = Math.Floor(Math.Log10(lambda.Last()));
-        nmsePlot.VisualProperties.XAxisMaximumFixedValue = Math.Ceiling(Math.Log10(lambda.Skip(1).First()));
-      }
-      nmsePlot.Rows["NMSE (train)"].VisualProperties.PointSize = 5;
-      nmsePlot.Rows["NMSE (test)"].VisualProperties.PointSize = 5;
+        nmsePlot.VisualProperties.XAxisMinimumFixedValue = Math.Pow(10, Math.Floor(Math.Log10(lambda.Last())));
+        nmsePlot.VisualProperties.XAxisMaximumFixedValue = Math.Pow(10, Math.Ceiling(Math.Log10(lambda.Skip(1).First())));
+      }
+      nmsePlot.Rows["NMSE (train)"].VisualProperties.ChartType = DataRowVisualProperties.DataRowChartType.Points;
+      nmsePlot.Rows["NMSE (test)"].VisualProperties.ChartType = DataRowVisualProperties.DataRowChartType.Points;
+      nmsePlot.Rows["Number of variables"].VisualProperties.ChartType = DataRowVisualProperties.DataRowChartType.Points;
+      nmsePlot.Rows["Number of variables"].VisualProperties.SecondYAxis = true;
+
 
       Results.Add(new Result(nmsePlot.Name, nmsePlot.Description, nmsePlot));